orbbec/OrbbecSDK

Orbbec SDK v1&v2 Pre-Compiled Repo

What it solves

It provides a unified software development kit (SDK) to interface with Orbbec's 3D cameras, allowing developers to capture data streams and control hardware across a wide range of device series (such as Gemini, Femto, and Astra).

How it works

The SDK acts as a bridge between the camera hardware and the application. It includes core libraries and C/C++ header files that allow developers to integrate camera functionality into their own projects. It supports both the newer UVC standard and legacy OpenNI protocols, ensuring compatibility with both current and older Orbbec products. It also provides a dedicated viewer tool, OrbbecViewer, for real-time data stream visualization and camera control.

Who it’s for

Developers building applications that require 3D sensing, depth perception, and computer vision, targeting platforms including Windows, Linux (x64 and ARM), and MacOS.

Highlights

  • Broad Device Support: Compatible with multiple product lines including Gemini, Femto, Astra, and LiDAR series.
  • C/C++ Integration: Provides core libraries and header files for native development.
  • Cross-Platform: Works across Windows, Linux (including NVIDIA Jetson and Raspberry Pi), and MacOS.
  • Unified Codebase: Enables developers to support both new and old products with a single set of code via built-in OpenNI protocol support.
  • Visualization Tool: Includes OrbbecViewer for easy camera testing and stream viewing.

Related

  • Project
    mjkwon2021/CAT-Net

    A network for detecting and localizing image manipulations by analyzing JPEG compression artifacts, providing tools for image forensics research.

  • Project
    fabiotosi92/ZipDepth

    ZipDepth is a 6 M‑parameter, zero‑shot monocular depth model that runs at >1 k FPS on GPUs and can be exported to mobile runtimes. It combines RepVGG‑style re‑parameterizable convolutions, strip‑pooling attention, and a lightweight FPN decoder. The repo provides ready‑to‑run inference scripts, ONNX/TorchScript export utilities, benchmarks, and full training pipelines (knowledge‑distilled from Depth Anything V2).

  • Project
    BuntingLabs/mundi.ai

    Mundi is an open source web GIS that uses LLMs to automate geoprocessing algorithms and symbology editing for vector, raster, and point cloud data.

  • Project
    OSU-NLP-Group/UGround

    UGround is an open‑source visual‑language model (2 B/7 B/72 B) fine‑tuned to locate UI elements in screenshots from a textual description. The repo ships pretrained weights, a >1 M‑image GUI grounding dataset, evaluation scripts for four benchmarks, and a Hugging Face demo. Inference runs via vLLM with a simple prompt that returns (x, y) coordinates. The 72 B model achieves state‑of‑the‑art scores on the ScreenSpot benchmark and is described in an ICLR 2025 oral paper.